Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1318 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1266270 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7924. Min Act: -0.0000

Data Index: 168935 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1701912 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1778803 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1341575 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8173. Min Act: -0.0000

Data Index: 686733 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7730. Min Act: -0.0000

Data Index: 626355 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.6784. Min Act: -0.0000

Data Index: 757456 (The Pile)

Max Activating Token Index: 272

Text #8

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1669027 (The Pile)

Max Activating Token Index: 579

Text #9

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1007545 (The Pile)

Max Activating Token Index: 26

Text #10

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.6506. Min Act: -0.0000

Data Index: 677684 (The Pile)

Max Activating Token Index: 28

Text #11

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1915655 (The Pile)

Max Activating Token Index: 959

Text #12

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1987400 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1069110 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1613028 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.6604. Min Act: -0.0000

Data Index: 739936 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1382914 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5739. Min Act: -0.0000

Data Index: 859975 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1204012 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1255591 (The Pile)

Max Activating Token Index: 935